[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M698ZZKWMNSGFB6MB0FCK084":3,"skill-same:01M698ZZKWMNSGFB6MB0FCK084":60},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":21,"linkOnly":22,"markdownContent":23,"markdownBody":24,"frontMatter":25,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M698ZZKWMNSGFB6MB0FCK084","agents-cli-langchain",null,"Use when working in this project — adding tools, editing the agent, running, evaluating, serving or deploying it — or when guidance mentions ADK, LlmAgent, google.adk, adk web, or an ADK runner. This project is LangChain\u002FLangGraph scaffolded by agents-cli, so ADK-specific instructions do not apply.","google\u002Fagents-cli","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M698ZVGDEBGAXVZGNKKKCRBQ",6336,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fextensions\u002Flangchain\u002Ftemplate\u002F.agents\u002Fskills\u002Fagents-cli-langchain\u002FSKILL.md",[],[19,20,9],"cli","agents cli langchain","2026-11-10 10:12:30",false,"---\nname: agents-cli-langchain\ndescription: >\n  Use when working in this project — adding tools, editing the agent, running,\n  evaluating, serving or deploying it — or when guidance mentions ADK, LlmAgent,\n  google.adk, adk web, or an ADK runner. This project is LangChain\u002FLangGraph\n  scaffolded by agents-cli, so ADK-specific instructions do not apply.\n---\n\n# LangChain project (agents-cli)\n\nThe agent is a compiled LangGraph graph exported as `root_agent` from\n`app\u002Fagent.py`. There is no `google.adk` dependency and no ADK runner. Other\n`google-agents-cli-*` skills assume ADK; where they describe the agent itself,\nthis skill wins.\n\n**Experimental, and Agent Runtime is degraded.** Deploy to cloud_run or gke. On\nagent_runtime the app serves, but `publish gemini` is refused, the Console\nplayground cannot invoke it, and Console sessions\u002Ftraces stay empty: all three want the\nADK `reasoning_engine` routes this project does not serve. Say so before recommending it.\n\n## What ADK guidance maps to here\n\n| ADK guidance | This project |\n|---|---|\n| `LlmAgent`, `Agent`, `google.adk.tools` | `langchain.agents.create_agent`, plain Python functions as tools, or any compiled `StateGraph` |\n| `adk web`, `adk run` | `agents-cli playground` (runs `langgraph dev`) |\n| ADK runner behind `agents-cli run` | `agents-cli run` invokes the graph in-process |\n| `agents-cli eval dataset synthesize`, `eval optimize` | Unavailable: both drive the agent through ADK. The command says so and exits |\n| Add an `LlmAgent` in `app\u002Fagent.py` | Change the graph in `app\u002Fagent.py`; keep the name `root_agent` |\n\n## The contract\n\nKeep these two, whatever you build inside them:\n\n- `app\u002Fagent.py` exports `root_agent`, a compiled graph with `messages` state.\n  Callers only use `root_agent.invoke({\"messages\": [...]})` and\n  `root_agent.astream(stream_mode=\"messages\")`.\n- `app\u002Ffast_api_app.py` exposes `app`. Every deployment target runs\n  `uvicorn app.fast_api_app:app`.\n\nAdding a tool means writing a typed function with a docstring and passing it in\n`tools=[...]`. Switching frameworks (LangGraph `StateGraph`,\n`deepagents.create_deep_agent`) means rewriting `app\u002Fagent.py` only. Pre-1.0\nLangChain (LCEL chains, `AgentExecutor`) is not supported: not compiled graphs.\n\n## Commands\n\n```bash\nagents-cli install                  # uv sync\nagents-cli playground               # langgraph dev, port 8080\nagents-cli run \"hello\"              # invoke the graph in-process\nagents-cli eval generate --dataset tests\u002Feval\u002Fdatasets\u002Fbasic-dataset.json -o tests\u002Feval\u002Foutput\u002F\nagents-cli eval grade --traces tests\u002Feval\u002Foutput\u002F\u003Cdataset>.json --config tests\u002Feval\u002Feval_config.yaml\nagents-cli deploy                   # unchanged\nagents-cli scaffold enhance -d cloud_run --cicd-runner github_actions   # add infra later\n```\n\n`playground`, `run` and `eval generate` are overridden by\n`agents-cli-extension.yaml` at the project root. Prefix any command with\n`AGENTS_CLI_DISABLE_OVERRIDES=1` to reach the built-in instead.\n\n## Serving\n\nA2A only: JSON-RPC at `POST \u002Fa2a\u002Fapp`, card at\n`\u002Fa2a\u002Fapp\u002F.well-known\u002Fagent-card.json`, health at `\u002Fhealth`. Token streaming\ncomes from `astream(stream_mode=\"messages\")`.\n\n## Common mistakes\n\n- Renaming `root_agent` or `app`, which breaks `run`, eval and deploy.\n- Reaching for `eval dataset synthesize` or `eval optimize`: they need ADK.\n  Write cases into `tests\u002Feval\u002Fdatasets\u002F` and use `eval generate` + `eval grade`.\n- Expecting `\u002Frun_sse` or ADK session routes; this server serves A2A.\n- Running `agents-cli run --url ...` against a deployed agent without\n  `AGENTS_CLI_DISABLE_OVERRIDES=1`, which invokes the local graph instead.\n- `run` and `eval generate` call Gemini on Gemini platform with ADC, so they need\n  `GOOGLE_CLOUD_PROJECT` and credentials, or `GOOGLE_API_KEY` \u002F `GEMINI_API_KEY`\n  in `.env`.\n\n## References\n\n- `references\u002Flangchain.md` — framework contract and per-command detail.\n- `references\u002Fsamples.md` — agents worth copying from, by shape.\n","# LangChain project (agents-cli)\n\nThe agent is a compiled LangGraph graph exported as `root_agent` from\n`app\u002Fagent.py`. There is no `google.adk` dependency and no ADK runner. Other\n`google-agents-cli-*` skills assume ADK; where they describe the agent itself,\nthis skill wins.\n\n**Experimental, and Agent Runtime is degraded.** Deploy to cloud_run or gke. On\nagent_runtime the app serves, but `publish gemini` is refused, the Console\nplayground cannot invoke it, and Console sessions\u002Ftraces stay empty: all three want the\nADK `reasoning_engine` routes this project does not serve. Say so before recommending it.\n\n## What ADK guidance maps to here\n\n| ADK guidance | This project |\n|---|---|\n| `LlmAgent`, `Agent`, `google.adk.tools` | `langchain.agents.create_agent`, plain Python functions as tools, or any compiled `StateGraph` |\n| `adk web`, `adk run` | `agents-cli playground` (runs `langgraph dev`) |\n| ADK runner behind `agents-cli run` | `agents-cli run` invokes the graph in-process |\n| `agents-cli eval dataset synthesize`, `eval optimize` | Unavailable: both drive the agent through ADK. The command says so and exits |\n| Add an `LlmAgent` in `app\u002Fagent.py` | Change the graph in `app\u002Fagent.py`; keep the name `root_agent` |\n\n## The contract\n\nKeep these two, whatever you build inside them:\n\n- `app\u002Fagent.py` exports `root_agent`, a compiled graph with `messages` state.\n  Callers only use `root_agent.invoke({\"messages\": [...]})` and\n  `root_agent.astream(stream_mode=\"messages\")`.\n- `app\u002Ffast_api_app.py` exposes `app`. Every deployment target runs\n  `uvicorn app.fast_api_app:app`.\n\nAdding a tool means writing a typed function with a docstring and passing it in\n`tools=[...]`. Switching frameworks (LangGraph `StateGraph`,\n`deepagents.create_deep_agent`) means rewriting `app\u002Fagent.py` only. Pre-1.0\nLangChain (LCEL chains, `AgentExecutor`) is not supported: not compiled graphs.\n\n## Commands\n\n```bash\nagents-cli install                  # uv sync\nagents-cli playground               # langgraph dev, port 8080\nagents-cli run \"hello\"              # invoke the graph in-process\nagents-cli eval generate --dataset tests\u002Feval\u002Fdatasets\u002Fbasic-dataset.json -o tests\u002Feval\u002Foutput\u002F\nagents-cli eval grade --traces tests\u002Feval\u002Foutput\u002F\u003Cdataset>.json --config tests\u002Feval\u002Feval_config.yaml\nagents-cli deploy                   # unchanged\nagents-cli scaffold enhance -d cloud_run --cicd-runner github_actions   # add infra later\n```\n\n`playground`, `run` and `eval generate` are overridden by\n`agents-cli-extension.yaml` at the project root. Prefix any command with\n`AGENTS_CLI_DISABLE_OVERRIDES=1` to reach the built-in instead.\n\n## Serving\n\nA2A only: JSON-RPC at `POST \u002Fa2a\u002Fapp`, card at\n`\u002Fa2a\u002Fapp\u002F.well-known\u002Fagent-card.json`, health at `\u002Fhealth`. Token streaming\ncomes from `astream(stream_mode=\"messages\")`.\n\n## Common mistakes\n\n- Renaming `root_agent` or `app`, which breaks `run`, eval and deploy.\n- Reaching for `eval dataset synthesize` or `eval optimize`: they need ADK.\n  Write cases into `tests\u002Feval\u002Fdatasets\u002F` and use `eval generate` + `eval grade`.\n- Expecting `\u002Frun_sse` or ADK session routes; this server serves A2A.\n- Running `agents-cli run --url ...` against a deployed agent without\n  `AGENTS_CLI_DISABLE_OVERRIDES=1`, which invokes the local graph instead.\n- `run` and `eval generate` call Gemini on Gemini platform with ADC, so they need\n  `GOOGLE_CLOUD_PROJECT` and credentials, or `GOOGLE_API_KEY` \u002F `GEMINI_API_KEY`\n  in `.env`.\n\n## References\n\n- `references\u002Flangchain.md` — framework contract and per-command detail.\n- `references\u002Fsamples.md` — agents worth copying from, by shape.\n",{"name":5,"description":7},"main","f4e994044164ff6617f0799900dba0fc091ef0e3","extensions\u002Flangchain\u002Ftemplate\u002F.agents\u002Fskills\u002Fagents-cli-langchain",733,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli","https:\u002F\u002Fgoogle.github.io\u002Fagents-cli\u002F","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-05 01:44:59",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add google\u002Fagents-cli --skill agents-cli-langchain",{"tool":42,"command":43},"bunx","bunx skills add google\u002Fagents-cli --skill agents-cli-langchain",{"tool":45,"command":46},"pnpm","pnpm dlx skills add google\u002Fagents-cli --skill agents-cli-langchain","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fextensions\u002Flangchain\u002Ftemplate\u002F.agents\u002Fskills\u002Fagents-cli-langchain\u002FSKILL.md",true,[50,56],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Flangchain.md","REFERENCE","参考文档",6065,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fextensions\u002Flangchain\u002Ftemplate\u002F.agents\u002Fskills\u002Fagents-cli-langchain\u002Freferences\u002Flangchain.md",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fsamples.md",3612,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fextensions\u002Flangchain\u002Ftemplate\u002F.agents\u002Fskills\u002Fagents-cli-langchain\u002Freferences\u002Fsamples.md",[61,99,121,144,169,188],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":80,"publishedAt":21},"01M6990ZGJV6CHR6CZK81S58CN","google-agents-cli-workflow","This skill should be used when the user wants to \"develop an agent\", \"build an agent using ADK\", \"run the agent locally\", \"debug agent code\", \"test an agent\", \"deploy an agent\", \"publish an agent\", \"monitor an agent\", or needs the ADK (Agent Development Kit) development lifecycle and coding guidelines. Entrypoint for building ADK agents. Always active — provides the full workflow (scaffold, build, evaluate, deploy, publish, observe), code preservation rules, model selection guidance, and troubleshooting steps for ADK or any agent development.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fagents\u002Fcli\u002Fskills\u002Fdata\u002Fgoogle-agents-cli-workflow\u002FSKILL.md",[67,72,75],{"categoryNo":68,"categoryName":69,"taxonomyType":70,"taxonomyTypeDesc":71},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",{"categoryNo":73,"categoryName":74,"taxonomyType":70,"taxonomyTypeDesc":71},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[9,81,19,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98],"google agents cli workflow","workflow","adk","agent development kit","agent development","development lifecycle","model","observe","selection","model selection","kit","uv","code","debug agent","publish","apache","active","run",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":107,"publishedAt":21},"01M6990XH0S4MNS7YTDAMNAAEW","google-agents-cli-scaffold","This skill should be used when the user wants to \"create an agent project\", \"start a new ADK project\", \"build me a new agent\", \"add CI\u002FCD to my project\", \"add deployment\", \"enhance my project\", or \"upgrade my project\". Part of the agents-cli skills suite. Covers `agents-cli scaffold create`, `scaffold enhance`, and `scaffold upgrade` commands, template options, deployment targets, and the prototype-first workflow. Do NOT use for writing agent code (ADK projects: use google-agents-cli-adk-code) or deployment operations (use google-agents-cli-deploy).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fagents\u002Fcli\u002Fskills\u002Fdata\u002Fgoogle-agents-cli-scaffold\u002FSKILL.md",[105,106],{"categoryNo":68,"categoryName":69,"taxonomyType":70,"taxonomyTypeDesc":71},{"categoryNo":73,"categoryName":74,"taxonomyType":70,"taxonomyTypeDesc":71},[108,9,19,109,83,110,111,112,113,114,92,115,82,93,116,117,96,118,119,120],"google agents cli scaffold","scaffold","writing","projects","new agent","project","ci","upgrade","create","me","options","template","CI\u002FCD",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":129,"publishedAt":21},"01M6990VP634A9G6052KQCZNYJ","google-agents-cli-publish","This skill should be used when the user wants to \"publish an agent\", \"publish my ADK agent\", \"register an agent with Gemini\", \"publish to Gemini\" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to \"manage agents in Agent Registry\", \"list\u002Fupdate\u002Fdelete registered agents\", or \"register an MCP server\". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fagents\u002Fcli\u002Fskills\u002Fdata\u002Fgoogle-agents-cli-publish\u002FSKILL.md",[127,128],{"categoryNo":68,"categoryName":69,"taxonomyType":70,"taxonomyTypeDesc":71},{"categoryNo":73,"categoryName":74,"taxonomyType":70,"taxonomyTypeDesc":71},[9,19,130,95,83,131,132,92,133,134,135,136,137,96,138,139,140,141,142,143],"google agents cli publish","MCP","programmatic","auto","mcp server","agent registry","server","delete","command","update","install","suite","fleet","registry",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":158,"publishedAt":21},"01M6990SFDY0JKXYP921BKRJYE","google-agents-cli-observability","This skill should be used when the user wants to \"set up tracing\", \"monitor my agent\", \"configure logging\", \"add observability\", \"debug production traffic\", or needs guidance on monitoring deployed agents, including ADK (Agent Development Kit) agents. Covers Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party integrations (AgentOps, Phoenix, MLflow, etc.), and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment setup (use google-agents-cli-deploy) or API code patterns (use google-agents-cli-adk-code).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fagents\u002Fcli\u002Fskills\u002Fdata\u002Fgoogle-agents-cli-observability\u002FSKILL.md",[150,153,154,155],{"categoryNo":151,"categoryName":152,"taxonomyType":70,"taxonomyTypeDesc":71},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":73,"categoryName":74,"taxonomyType":70,"taxonomyTypeDesc":71},{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},{"categoryNo":156,"categoryName":157,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000033","数据分析师",[9,19,159,160,83,84,85,161,162,91,92,163,164,165,93,166,167,96,140,168],"google agents cli observability","observability","SET","up","traffic","configure","code patterns","api","monitoring","mlflow",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":177,"publishedAt":21},"01M6990PXZ0S6NHYV8PGGVFT6E","google-agents-cli-eval","This skill should be used when the user wants to \"run an evaluation\", \"evaluate my agent\", \"evaluate my ADK agent\", \"write an eval dataset\", \"analyze eval failures\", \"compare eval results\", \"optimize agent\", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fagents\u002Fcli\u002Fskills\u002Fdata\u002Fgoogle-agents-cli-eval\u002FSKILL.md",[175,176],{"categoryNo":73,"categoryName":74,"taxonomyType":70,"taxonomyTypeDesc":71},{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},[9,19,178,179,83,180,113,181,92,182,165,93,183,166,184,185,186,96,98,187],"google agents cli eval","eval","project scaffolding","scaffolding","dataset","scoring","common","analyze","optimize","write",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":200,"publishedAt":21},"01M6990MAHH0X6XCNVB74Q67P6","google-agents-cli-deploy","This skill should be used when the user wants to \"deploy an agent\", \"deploy my ADK agent\", \"set up CI\u002FCD\", \"configure secrets\", \"troubleshoot a deployment\", or needs guidance on Agent Runtime, Cloud Run, or GKE deployment targets, or binding an agent to an Agent Gateway. Covers deployment workflows, service accounts, rollback, and production infrastructure. Applies to any framework agents-cli deploys (ADK, LangChain, ...). Part of the agents-cli skills suite. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), evaluation (use google-agents-cli-eval), or project scaffolding (use google-agents-cli-scaffold).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fagents-cli\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fagents\u002Fcli\u002Fskills\u002Fdata\u002Fgoogle-agents-cli-deploy\u002FSKILL.md",[194,197,198,199],{"categoryNo":195,"categoryName":196,"taxonomyType":70,"taxonomyTypeDesc":71},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":68,"categoryName":69,"taxonomyType":70,"taxonomyTypeDesc":71},{"categoryNo":73,"categoryName":74,"taxonomyType":70,"taxonomyTypeDesc":71},{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},[9,201,19,202,83,113,114,179,92,203,165,204,98,205,206,207,208,209,210,211],"google agents cli deploy","deploy","workflows","gke","Evaluation","langchain","infrastructure","do","cloud run","for","deployment"]